Multiple Diseases Detection

Abstract

The rapid advancement of deep learning and computer vision has enabled development of intelligent systems capable of detecting multiple diseases simultaneously from medical imaging data. This project proposes a Multi Disease Detection System integrating Brain Tumor detection from MRI scans and Pneumonia detection from chest X-ray images into a unified deep learning framework. Brain tumors one of the most life-threatening forms of cancer are detected from MRI images using a Convolutional Neural Network(CNN) Pneumonia, a leading cause of mortality worldwide particularly in children under five, is detected from chest X-ray images using transfer learning models including VGG16 and ResNet50 fine-tuned on the Kaggle Chest X-Ray Pneumonia dataset. The proposed system employs a dual-model architecture sharing a common preprocessing pipeline. Both models are trained on established benchmark datasets BraTS for brain tumors and the Kaggle Chest X-Ray dataset for pneumonia and evaluated using accuracy, precision, recall, F1-score, and AUC-ROC metrics. The combined system achieves high accuracy in both diagnostic tasks, offering a cost- effective, non-invasive, automated decision-support tool suitable for clinical environments, especially in resource-limited healthcare settings where specialist availability is scarce.

Introduction

The text presents a unified AI-based Multi-Disease Detection System designed to detect brain tumors from MRI scans and pneumonia from chest X-rays using deep learning and transfer learning.

• Purpose: Medical imaging enables non-invasive diagnosis, but traditional manual interpretation can be slow, expensive, and affected by human error and observer variability.
• Proposed system: Uses CNN-based models such as ResNet50 and VGG16 to perform:
  • Brain tumor classification into Glioma, Meningioma, Pituitary Tumor, and No Tumor.
  • Pneumonia classification into Normal or Pneumonia.
• Image processing: A common preprocessing pipeline uses resizing, normalization, rotation, flipping, and zooming to improve model robustness.
• Datasets: The system uses benchmark datasets such as the BraTS Brain MRI Dataset and Kaggle Chest X-ray Pneumonia Dataset.
• Evaluation: Performance is measured using Accuracy, Precision, Recall, F1-score, ROC-AUC, and Confusion Matrix.
• Clinical significance: The system aims to support early diagnosis, reduce radiologists' workload, minimize diagnostic errors, and improve healthcare access in rural and resource-limited areas.
• Explainability: Techniques such as Grad-CAM can highlight affected regions in medical images, helping clinicians understand and trust AI predictions.
• Literature findings: Existing research includes classical machine learning, CNNs, transfer learning, explainable AI, attention mechanisms, and multimodal deep learning. Many reported high accuracies, but most systems focus on only one disease.
• Research gaps: The major limitations identified are:
  1. Single-disease detection.
  2. Lack of an integrated multi-disease framework.
  3. Dependence on limited datasets and poor generalization.
  4. Scalability and real-world clinical deployment challenges.
• Future scope: The proposed system can be expanded to include more diseases, stronger XAI techniques, and deployment on cloud and mobile platforms.

Conclusion

This survey paper reviewed various deep learning and transfer learning techniques used for brain tumor and pneumonia detection from medical images. The literature analysis indicates that CNN-based models such as VGG16, ResNet50, and DenseNet achieve high diagnostic accuracy and can effectively assist healthcare professionals in disease detection. The study also identified the need for integrated multi-disease diagnostic systems. To address this gap, the proposed Multiple Disease Detection System combines brain tumor classification and pneumonia detection within a unified framework. Such a system can provide accurate, cost-effective, and automated diagnostic support, contributing to early disease detection and improved healthcare decision-making.

References

[1] P. Rajpurkar, J. Irvin, K. Zhu, B. Yang, H. Mehta, T. Duan, D. Ding, A. Bagul, R. L. Ball, C. Langlotz, K. Shpanskaya, M. P. Lungren, and A. Y. Ng, \"CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning,\" arXiv preprint arXiv:1711.05225v3, Dec. 2017. [2] H. Mohsen, E.-S. A. El-Dahshan, E.-S. M. El-Horbaty, and A.-B. M. Salem, \"Classification using deep learning neural networks for brain tumors,\" Future Comput. Informatics J., vol. 3, no. 1, pp. 68–71, 2018. doi: 10.1016/j.fcij.2017.12.001. [3] A. Anil, A. Raj, H. A. Sarma, N. Chandran, and D. P. Lal, \"Brain Tumor Detection from Brain MRI Using Deep Learning,\" Int. J. Innovative Res. Appl. Sci. Eng. (IJIRASE), vol. 3, no. 2, pp. 458–465, Aug. 2019. doi: 10.29027/IJIRASE.v3.i2.2019. [4] D. T. R., K. K., R. T. S., and K. S., \"Pneumonia Detection Using Chest X-Ray with Deep Learning,\" Int. Res. J. Eng. Technol. (IRJET), vol. 7, no. 4, pp. 2751–2754, Apr. 2020. [5] M. Sharma, P. Sharma, R. Mittal, and K. Gupta, \"Brain Tumour Detection Using Machine Learning,\" J. Electron. Informatics, vol. 3, no. 4, pp. 298–308, Dec. 2021. doi: 10.36548/jei.2021.4.005. [6] N. Sravanthi, N. Swetha, P. R. Devi, S. Rachana, S. Gothane, and N. Sateesh, \"Brain Tumor Detection using Image Processing,\" Int. J. Sci. Res. Comput. Sci. Eng. Inf. Technol. (IJSRCSEIT), vol. 7, no. 3, pp. 348–352, May–Jun. 2021. doi: 10.32628/CSEIT217384. [7] S. L. Bangare, H. S. Rajankar, P. S. Patil, K. V. Nakum, and G. S. Paraskar, \"Pneumonia Detection and Classification using CNN and VGG16,\" Int. J. Adv. Res. Sci. Commun. Technol. (IJARSCT), vol. 2, no. 3, pp. 771–779, May 2022. doi: 10.48175/IJARSCT-3851. [8] Y. Wang, C. Liu, Y. Fan, C. Niu, W. Huang, Y. Pan, J. Li, Y. Wang, and J. Li, \"A multi-modal deep learning solution for precise pneumonia diagnosis: the PneumoFusion-Net model,\" Front. Physiol., vol. 16, p. 1512835, Mar. 2025. doi: 10.3389/fphys.2025.1512835. [9] P. Mooney, \"Chest X-Ray Images (Pneumonia),\" Kaggle, 2018. [Online]. Available: https://www.kaggle.com/paultimothymooney/chest-xray-pneumonia. [10] B. H. Menze et al., \"The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS),\" IEEE Trans. Med. Imaging, vol. 34, no. 10, pp. 1993–2024, Oct. 2015. doi: 10.1109/TMI.2014.2377694. [11] K. Simonyan and A. Zisserman, \"Very Deep Convolutional Networks for Large-Scale Image Recognition,\" in Proc. ICLR, 2015. arXiv:1409.1556. [12] K. He, X. Zhang, S. Ren, and J. Sun, \"Deep Residual Learning for Image Recognition,\" in Proc. IEEE CVPR, 2016, pp. 770–778. doi: 10.1109/CVPR.2016.90. [13] G. Huang, Z. Liu, L. Van der Maaten, and K. Q. Weinberger, \"Densely Connected Convolutional Networks,\" in Proc. IEEE CVPR, 2017, pp. 4700–4708. doi: 10.1109/CVPR.2017.243.

Copyright

Copyright © 2026 Mrs. Pushpa R N, Sahana H M, Sanjana Ishwar Naik, Sanjana N, Srusti K. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.